© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108332
    Prev
    Next
    INDEX
    Explanations

    <|end|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elastic
    -0.08
    hers
    -0.08
    werken
    -0.08
    Elastic
    -0.08
    elastic
    -0.08
    पति
    -0.07
    ",@"
    -0.07
    tersuch
    -0.07
     elastic
    -0.07
     Tomas
    -0.07
    POSITIVE LOGITS
    Ah
    0.09
    Hm
    0.08
     Ha
    0.08
     Ah
    0.07
    آن
    0.07
     стих
    0.07
     Co
    0.07
     사이
    0.07
     جمله
    0.07
    анг
    0.07
    Activations Density 0.066%

    No Known Activations